i verified i have cuda 12.8 and have the latest working kohya and swarm. fp16 image2vid works, just
i verified i have cuda 12.8 and have the latest working kohya and swarm. fp16 image2vid works, just takes a long time at the LoRA step.
B@Dr. Furkan Gözükara can you tell me something one this , like how he is able to do it with negative prompting
Fye for debugging reason
Fuse de distilled model
XERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/convert-caffe2-to-onnx
ERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/convert-onnx-to-caffe2
ERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/torchfrtrace
ERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/torchrun
ERROR: Could not install packages due to an OSError: [Errno 122] Disk quota exceeded
ERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/convert-onnx-to-caffe2
ERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/torchfrtrace
ERROR: Failed to restore /workspace/supir files/SUPIR/venv/bin/torchrun
ERROR: Could not install packages due to an OSError: [Errno 122] Disk quota exceeded
Fcfg 3.5 and negative prompt
Fyour disk is out of space
Fdelete pod and expand
Xso I delete pod then deploy a bigger pod under same storage
Fsent you file
Fedit your network volume and expand
F@Random#7680174
F
Xokay thanks
XMy workspace got messy so quickly
Xgetting this error now Enter your choice (1-2): 2
Please select an option:
1. Start With Light Theme
2. Start With Dark Theme
Enter your choice (1-2): 1
Traceback (most recent call last):
File "/workspace/SUPIR/gradio_demo.py", line 14, in <module>
import einops
Please select an option:
1. Start With Light Theme
2. Start With Dark Theme
Enter your choice (1-2): 1
Traceback (most recent call last):
File "/workspace/SUPIR/gradio_demo.py", line 14, in <module>
import einops
XThis is in trying to install supir
B@Dr. Furkan Gözükara why its using only one gpu if we have 4 here ?
Frm -r supir
Fre install from fresh
Fwhich app?
Brunpod
Fit is not an app
Bnvitop
Bin runpod i am using L40 with 4 gpu and with swernui person implimentation
https://www.youtube.com/watch?v=-uhL2nW7Ddw&ab_channel=SECourses
@Dr. Furkan Gözükara
https://www.youtube.com/watch?v=-uhL2nW7Ddw&ab_channel=SECourses
@Dr. Furkan Gözükara
YouTubeSECourses
Unlock the power of FLUX LoRA training, even if you're short on GPUs or looking to boost speed and scale! This comprehensive guide takes you from novice to expert, showing you how to use Kohya GUI for creating top-notch FLUX LoRAs in the cloud. We'll cover everything: maximizing quality, optimizing speed, and finding the best deals. With our exc...
Fdid you load 4x gpu config?
Ftell me your config name
Brank1 slow config file
Brank1 slow 28700mb slow
Fit is wrong
F
Fand only lora works with 48gb gpus for 4x
Bokay thanks and everything is same like in the vedio
Fyes
B@Dr. Furkan Gözükara if i let it fininsh it with this 1gpu usage it will take more time but everything else will be same like results right /
B?
F4x gpu will reduce quality slightly
Fsince increases batch size
Areduce quality = less similarity with subject
or
reduce quality= lower resolution results / noise appearance?
or
reduce quality= lower resolution results / noise appearance?
Fless similarity
Xroot@9cb546417a6e:/workspace/SUPIR# rm -r supir
rm: cannot remove 'supir': No such file or directory
rm: cannot remove 'supir': No such file or directory
Xim getting that error
Fand type again
Frm -r SUPIR
B@Dr. Furkan Gözükara from where can i get those saved config before traing which we saved before starting the training
Fwhat do you mean
Bbefore starting the training we saved the cofig so i want to use that i got them
Bthanks fro response
Fcheck folders
Fprobably in workspace
